{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/music-tagging","name":"Music Tagging","slug":"music-tagging","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":35,"papers_with_code":22,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/magnatagatune","name":"MagnaTagATune","full_name":"","num_papers_in_archive":65},{"url":"/dataset/emopia","name":"EMOPIA","full_name":"A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation","num_papers_in_archive":23},{"url":"/dataset/atd-dataset","name":"ATD-Dataset","full_name":"Auto-Tune Detection Dataset (ATD-Dataset)","num_papers_in_archive":1},{"url":"/dataset/piast","name":"PIAST","full_name":"PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Text","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":35,"of":35,"of_with_code":22,"tagged_in_all":35,"counts":{"archive_papers_tagged":35,"with_a_code_link":22,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":35,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/convolutional-recurrent-neural-networks-for-1","slug":"convolutional-recurrent-neural-networks-for-1","title":"Convolutional Recurrent Neural Networks for Music Classification","date":"2016-09-14","arxiv_id":"1609.04243","repositories_listed":13,"syntology":null},{"url":"/paper/automatic-tagging-using-deep-convolutional","slug":"automatic-tagging-using-deep-convolutional","title":"Automatic tagging using deep convolutional neural networks","date":"2016-06-01","arxiv_id":"1606.00298","repositories_listed":11,"syntology":null},{"url":"/paper/transfer-learning-for-music-classification","slug":"transfer-learning-for-music-classification","title":"Transfer learning for music classification and regression tasks","date":"2017-03-27","arxiv_id":"1703.09179","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/transfer-learning-for-music-classification#ran","syntology_url":"https://syntology.ai/paper/1703.09179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.09179"}},"official":{"repos":["keunwoochoi/transfer_learning_music"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/m2d2-exploring-general-purpose-audio-language","slug":"m2d2-exploring-general-purpose-audio-language","title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","date":"2025-03-28","arxiv_id":"2503.22104","repositories_listed":2,"syntology":null},{"url":"/paper/audiolime-listenable-explanations-using","slug":"audiolime-listenable-explanations-using","title":"audioLIME: Listenable Explanations Using Source Separation","date":"2020-08-02","arxiv_id":"2008.00582","repositories_listed":2,"syntology":null},{"url":"/paper/semantic-aware-interpretable-multimodal-music","slug":"semantic-aware-interpretable-multimodal-music","title":"Semantic-Aware Interpretable Multimodal Music Auto-Tagging","date":"2025-05-22","arxiv_id":"2505.17233","repositories_listed":1,"syntology":null},{"url":"/paper/masked-latent-prediction-and-classification","slug":"masked-latent-prediction-and-classification","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","date":"2025-02-17","arxiv_id":"2502.12031","repositories_listed":1,"syntology":null},{"url":"/paper/muq-self-supervised-music-representation","slug":"muq-self-supervised-music-representation","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","date":"2025-01-02","arxiv_id":"2501.01108","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/muq-self-supervised-music-representation#ran","syntology_url":"https://syntology.ai/paper/2501.01108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.01108"}},"official":{"repos":["tencent-ailab/muq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/piast-a-multimodal-piano-dataset-with-audio","slug":"piast-a-multimodal-piano-dataset-with-audio","title":"PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Text","date":"2024-11-04","arxiv_id":"2411.02551","repositories_listed":1,"syntology":null},{"url":"/paper/towards-training-music-taggers-on-synthetic","slug":"towards-training-music-taggers-on-synthetic","title":"Towards Training Music Taggers on Synthetic Data","date":"2024-07-02","arxiv_id":"2407.02156","repositories_listed":1,"syntology":null},{"url":"/paper/an-experimental-comparison-of-multi-view-self","slug":"an-experimental-comparison-of-multi-view-self","title":"An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging","date":"2024-04-14","arxiv_id":"2404.09177","repositories_listed":1,"syntology":null},{"url":"/paper/perceptual-musical-features-for-interpretable","slug":"perceptual-musical-features-for-interpretable","title":"Perceptual Musical Features for Interpretable Audio Tagging","date":"2023-12-18","arxiv_id":"2312.11234","repositories_listed":1,"syntology":null},{"url":"/paper/employing-crowdsourcing-for-enriching-a-music","slug":"employing-crowdsourcing-for-enriching-a-music","title":"Employing Crowdsourcing for Enriching a Music Knowledge Base in Higher Education","date":"2023-06-12","arxiv_id":"2306.07310","repositories_listed":1,"syntology":null},{"url":"/paper/mulan-a-joint-embedding-of-music-audio-and","slug":"mulan-a-joint-embedding-of-music-audio-and","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","date":"2022-08-26","arxiv_id":"2208.12415","repositories_listed":1,"syntology":null},{"url":"/paper/s3t-self-supervised-pre-training-with-swin","slug":"s3t-self-supervised-pre-training-with-swin","title":"S3T: Self-Supervised Pre-training with Swin Transformer for Music Classification","date":"2022-02-21","arxiv_id":"2202.10139","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-affective-representations-of-music","slug":"enhancing-affective-representations-of-music","title":"Enhancing Affective Representations of Music-Induced EEG through Multimodal Supervision and latent Domain Adaptation","date":"2022-02-20","arxiv_id":"2202.09750","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-source-separation-by-steering","slug":"unsupervised-source-separation-by-steering","title":"Unsupervised Source Separation By Steering Pretrained Music Models","date":"2021-10-25","arxiv_id":"2110.13071","repositories_listed":1,"syntology":null},{"url":"/paper/codified-audio-language-modeling-learns","slug":"codified-audio-language-modeling-learns","title":"Codified audio language modeling learns useful representations for music information retrieval","date":"2021-07-12","arxiv_id":"2107.05677","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/codified-audio-language-modeling-learns#ran","syntology_url":"https://syntology.ai/paper/2107.05677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05677"}},"official":{"repos":["p-lambda/jukemir"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-modulation-front-end-for-music-audio","slug":"a-modulation-front-end-for-music-audio","title":"A Modulation Front-End for Music Audio Tagging","date":"2021-05-25","arxiv_id":"2105.11836","repositories_listed":1,"syntology":null},{"url":"/paper/melon-playlist-dataset-a-public-dataset-for","slug":"melon-playlist-dataset-a-public-dataset-for","title":"Melon Playlist Dataset: a public dataset for audio-based playlist generation and music tagging","date":"2021-01-30","arxiv_id":"2102.00201","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-metric-learning-for-tag-based","slug":"multimodal-metric-learning-for-tag-based","title":"Multimodal Metric Learning for Tag-based Music Retrieval","date":"2020-10-30","arxiv_id":"2010.16030","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-audio-signal-preprocessing","slug":"a-comparison-of-audio-signal-preprocessing","title":"A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging","date":"2017-09-06","arxiv_id":"1709.01922","repositories_listed":1,"syntology":null},{"url":null,"slug":"cmi-bench-a-comprehensive-benchmark-for","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","date":"2025-06-14","arxiv_id":"2506.12285","repositories_listed":0,"syntology":null},{"url":null,"slug":"music-foundation-model-as-generic-booster-for","title":"Music Foundation Model as Generic Booster for Music Downstream Tasks","date":"2024-11-02","arxiv_id":"2411.01135","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-music-and-language-attention-models-for","title":"Joint Music and Language Attention Models for Zero-shot Music Tagging","date":"2023-10-16","arxiv_id":"2310.10159","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-contrastive-learning-in-music-video","title":"Towards Contrastive Learning in Music Video Domain","date":"2023-09-01","arxiv_id":"2309.00347","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-front-ends-based-on-temporal","title":"Learnable Front Ends Based on Temporal Modulation for Music Tagging","date":"2022-11-28","arxiv_id":"2211.15254","repositories_listed":0,"syntology":null},{"url":null,"slug":"music-to-text-synaesthesia-generating","title":"Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings","date":"2022-10-02","arxiv_id":"2210.00434","repositories_listed":0,"syntology":null},{"url":null,"slug":"muslcat-multi-scale-multi-level-convolutional","title":"MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms","date":"2021-04-06","arxiv_id":"2104.02309","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-label-noise-on-a-music-tagger","title":"The Impact of Label Noise on a Music Tagger","date":"2020-08-14","arxiv_id":"2008.06273","repositories_listed":0,"syntology":null},{"url":null,"slug":"tensorflow-audio-models-in-essentia","title":"TensorFlow Audio Models in Essentia","date":"2020-03-16","arxiv_id":"2003.07393","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-embedded-cnn-for-music-tagging","title":"Multi-scale Embedded CNN for Music Tagging (MsE-CNN)","date":"2019-06-16","arxiv_id":"1906.06746","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effects-of-noisy-labels-on-deep","title":"The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging","date":"2017-06-07","arxiv_id":"1706.02361","repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-topological-persistence-in","title":"Applying Topological Persistence in Convolutional Neural Network for Music Audio Signals","date":"2016-08-26","arxiv_id":"1608.07373","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-variational-hierarchical-em-algorithm-for","title":"The variational hierarchical EM algorithm for clustering hidden Markov models","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/task/music-tagging/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/music-tagging/papers/ran/1","json":"/task/music-tagging/papers/ran/1.json","rows":3}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"9fc4f72111053e1e00ba2f0414105a03ed2790faa8c25657cf422ad13be50782","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}